Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 765 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7288. Min Range: -1.7288

Max Act: 1.7288. Min Act: -0.0000

Data Index: 875705 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 1.7288. Min Range: -1.7288

Max Act: 1.0901. Min Act: -0.0000

Data Index: 1848216 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.8754. Min Act: -0.0000

Data Index: 708065 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.7136. Min Act: -0.0000

Data Index: 754122 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.9526. Min Act: -0.0000

Data Index: 654870 (The Pile)

Max Activating Token Index: 170

Text #5

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1667242 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.9018. Min Act: -0.0000

Data Index: 273212 (The Pile)

Max Activating Token Index: 573

Text #7

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.8585. Min Act: -0.0000

Data Index: 814702 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.8883. Min Act: -0.0000

Data Index: 529589 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1156089 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.7561. Min Act: -0.0000

Data Index: 709522 (The Pile)

Max Activating Token Index: 481

Text #11

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.8211. Min Act: -0.0000

Data Index: 309003 (The Pile)

Max Activating Token Index: 60

Text #12

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1918256 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1363203 (The Pile)

Max Activating Token Index: 761

Text #14

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1106981 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1917637 (The Pile)

Max Activating Token Index: 889

Text #16

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1420582 (The Pile)

Max Activating Token Index: 91

Text #17

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1606480 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1704360 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 1.7288. Min Range: -1.7288

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1105532 (The Pile)

Max Activating Token Index: 65